# GPT-5.5 漏洞赏金计划

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：Murfalo
- 发布时间：2026-04-26 05:00
- AIHOT 分数：63
- AIHOT 链接：https://aihot.virxact.com/items/cmoeuhj4z01ogslb8jr8lpf87
- 原文链接：https://openai.com/index/gpt-5-5-bio-bug-bounty

## AI 摘要

OpenAI针对GPT-5.5生物信息处理功能启动了漏洞赏金计划，旨在激励安全研究人员发现并报告系统在生物信息相关任务中可能存在的漏洞、偏见或有害输出。该计划覆盖文本生成、数据分析及预测模型等多个应用场景，重点关注可能引发实际生物安全风险或伦理问题的缺陷。根据漏洞严重程度，报告者最高可获得2万美元奖金。此举旨在通过社区协作提前识别风险，强化模型在敏感领域的可靠性与安全性。

## 正文

GPT-5.5 Bio Bug Bounty | OpenAI

GPT-5.5 Bio Bug Bounty | OpenAI

April 23, 2026

Safety

GPT‑5.5 Bio Bug Bounty

Testing universal jailbreaks for biorisks in GPT‑5.5

Apply here(opens in a new window)

Invitation

As part of our ongoing efforts to strengthen our safeguards for advanced AI capabilities in biology, we’re introducing a Bio Bug Bounty for GPT‑5.5 and accepting applications. We’re inviting researchers with experience in AI red teaming, security, or biosecurity to try to find a universal jailbreak that can defeat our five-question bio safety challenge.

Program overview

Model in scope: GPT‑5.5 in Codex Desktop only. Challenge: Identify one universal jailbreaking prompt to successfully answer all five bio safety questions from a clean chat without prompting moderation. Rewards: $25,000 to the first true universal jailbreak to clear all five questions. Smaller awards may be granted for partial wins at our discretion.

Timeline:Applications open April 23, 2026 with rolling acceptances, and close on June 22, 2026. Testing begins April 28, 2026 and ends on July 27, 2026. Access: Application and invites. We will extend invitations to a vetted list of trusted bio red-teamers, and review new applications. Once selected, successful applicants will be onboarded to the bio bug bounty platform. Disclosure: All prompts, completions, findings, and communications are covered by NDA.

How to participate

Submit a short application here⁠⁠(opens in a new window) (name, affiliation, experience) by June 22, 2026. Accepted applicants and collaborators must have existing ChatGPT accounts to apply, and will sign a NDA. Apply now and help us make frontier AI safer.

If you’re interested in supporting OpenAI’s work to deliver safe and secure artificial intelligence beyond the Bio Bounty program, you can learn about our Safety Bug Bounty⁠(opens in a new window) and Security Bug Bounty⁠(opens in a new window)⁠ programs.

Keep reading

View all

Advancing youth safety and opportunity through global leadership Global Affairs Jun 2, 2026

A shared playbook for trustworthy third party evaluations Safety May 29, 2026

OpenAI’s Frontier Governance Framework Safety May 28, 2026